LEARNING TOOLS FOR BLOOD CELL SEGMENTATION AND
EXTRACTION TECHNIQUES
POON CHEE LIM
A project report submitted in partial fulfilment of the
requirements for the award of the degree of
Master of Engineering (Electrical - Computer and Microelectronic System)
Faculty of Electrical Engineering
Universiti Teknologi Malaysia
JANUARY 2013
LEARNING TOOLS FOR BLOOD CELL SEGMENTATION AND
EXTRACTION TECHNIQUES
POON CHEE LIM
UNIVERSITI TEKNOLOGI MALAYSIA
To my parents and God for always being there.
ACKNOWLEDGEMENT
During the writing of this thesis I was assisted by many individuals with
whom I would like to share my sincerest gratitude.
First and foremost I would like to express my appreciation to Dr. Nasrul
Humaimi Mahmood, my project supervisor for all his time, effort and guidance in
ensuring that I am able to complete this thesis. I would also like to thank him for all
his advice and also for the motivation he has given me throughout this time.
Next I would like to give my heartfelt thanks to my parents who have
supported me the whole time.
I would also like to express my thanks to all my friends who have been
supportive during this time and even providing some light hearted entertainment
throughout the writing of this thesis.
They also helped give me ideas and
encouragement.
Finally, I would also like to thank Faculty of Electrical Engineering,
Universiti Teknologi Malaysia and School of Graduate Studies (SPS UTM) for their
support in this project.
v
ABSTRACT
Blood cell segmentation and identification is vital in the study of blood as a
health indicator. A complete blood count is used to determine the state of a person’s
health based on the contents of the blood in particular the white blood cells and the
red blood cells. The main problem arises when massive amounts of blood samples
are required to be processed by the haematologist or Medical Laboratory
Technicians. The time and skill required for the task limits the speed and accuracy
with which the blood sample can be processed. This project aims to provide userfriendly software based on MATLAB allowing for quick user interaction with a
simple tool for the segmentation and identification of red and white blood cells from
a provided image.
The project presents the solution in a modular framework
allowing for future development within a structured environment.
In order to
perform the segmentation, this project uses k-means clustering and colour based
segmentation using International Commission on Illumination L*a*b* (CIELAB)
colour space coupled with polygon information of the region of interest. The project
integrates these methods into a flow within a Graphical User Interface (GUI) with
customizable variables to handle changing input images. The result of the project is
a working GUI with the capability to accept user interaction. The completed project
is able to obtain quick and accurate blood cell segmentation of both red and white
blood cells. The accuracy of this project ranges from 64% to 87% depending on the
type of processing used and the type of cells being extracted.
vi
ABSTRAK
Segmentasi dan pengenalan sel darah adalah penting dalam kajian darah
sebagai petunjuk kesihatan. Pengiraan darah lengkap digunakan untuk menentukan
tahap kesihatan seseorang berdasarkan kandungan sel darah putih merah. Masalah
timbul apabila kuantiti sampel darah yang perlu diproses oleh haematologist atau
Juruteknik Makmal Perubatan adalah besar. Masa dan kemahiran yang diperlukan
menghadkan kelajuan dan ketepatan pemprosesan sampel darah.
Projek ini
menyediakan perisian yang membolehkan interaksi pengguna yang cepat dan mudah
digunakan untuk segmentasi dan pengenalpastian sel darah merah dan putih dari imej
yang disediakan. Projek ini membentangkan penyelesaian dalam bentuk rangka
modular yang membenarkan pembangunan masa depan dalam persekitaran teratur.
Dalam
usaha
untuk
melaksanakan
segmentasi,
projek
ini
menggunakan
pengelompokan k-means dan segmentasi berasaskan warna dalam ruang warna
“International Commission on Illumination L*a*b*” bergandingan dengan
penggunaan maklumat poligon. Projek ini mengintegrasikan kaedah ini dalam antara
muka grafik pengguna (GUI) beserta dengan pembolehubah yang boleh diubah untuk
memproses input yang berlainan.
Hasil projek adalah GUI yang mempunyai
keupayaan untuk berinteraksi dengan pengguna. Secara keseluruhan, projek ini
berupaya mengendalikan segmentasi sel darah dengan cepat dan tepat untuk sel
darah merah dan putih. Ketepatan projek ini adalah diantara 64% sehingga 87%
bergantung kepada proses yang digunakan dan jenis sel yang hendak diekstrak.